# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
theme(legend.position = "top") +
xlim(-10, 90) +
theme_bw()
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 70) +
guides(fill="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
theme(legend.position = "top") +
xlim(-10, 90) +
theme_bw()
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 70) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
theme(legend.position = "top") +
xlim(-10, 90) +
theme_bw()
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
# plotting contributing linsear writing formula
contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-30, 30) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 70) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw(legend.position = "top")
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw(legend.position = "left")
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme(legend.position = "left")
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme(legend.position = "left") +
theme_bw()
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw(legend.position = "left")
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
opts(legend.position = "left") +
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme(legend.position = "left") +
theme_bw()
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "left")
contributing_reading_ease
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
readme_reading_ease
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw()
grid.arrange(readme_reading_ease, readme_reading_time, contributing_reading_ease, contributing_reading_time_plot, nrow = 2)
grid.arrange(readme_reading_ease, readme_reading_time_plot, contributing_reading_ease, contributing_reading_time_plot, nrow = 2)
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
# establishing the color scheme
irisColors <-
setNames( c('red', 'forestgreen', 'blue')
, levels(contributing_df$subdir)  )
# establishing the color scheme
subdirColors <-
setNames( c('red', 'forestgreen', 'blue')
, levels(contributing_df$subdir)  )
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
contributing_reading_ease
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw()
#plot of reading_ease
#readme_df <- readme_df |>
#  mutate(coef_grouping <- as.factor(subdir))
#test_lm <- lm(mcalpine_eflaw ~ word_count + as.factor(subdir),data=readme_df)
#summary(test_lm)
aggregate(contributing_df[, 3:10], list(contributing_df$subdir), median)
readme_reading_time_plot
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
readme_reading_ease
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw()
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw() +
theme(axis.text.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw(axis.text.y=element_blank()) +
theme(axis.text.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 100) +
guides(fill="none", color="none")+
theme_bw() +
theme(axis.text.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 110) +
guides(fill="none", color="none")+
theme_bw() +
theme(axis.text.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 140) +
guides(fill="none", color="none")+
theme_bw() +
theme(axis.text.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 140) +
guides(fill="none", color="none")+
theme_bw() +
theme(axis.title.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 140) +
guides(fill="none", color="none")+
theme_bw()
#theme(axis.title.y=element_blank())
readme_reading_time_plot
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 140) +
guides(fill="none", color="none")+
theme_bw()
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
guides(fill="none", color="none")+
theme_bw()
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2, labels = c("a)","b)"))
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
library(ggpubr)
ggarrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2,labels = c("a)","b)") )
ggarrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, ncol = 2, nrow = 2,labels = c("a)","b)") )
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
ylab("readme density") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
ylab("contributing density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
ylab("contributing density") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
library(tidyverse)
library(plyr)
library(gridExtra)
library(ggpubr)
# script for the analysis of document readability metrics
# readability metrics will be studied controlled by their length
# gaughan@u.northwestern.edu
# loading in the data
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../text_analysis/draft_readability_readme.csv")
contributing_df <- read_csv("../text_analysis/draft_readability_contributing.csv")
#getting basic stats for the readme readability
median(readme_df$flesch_reading_ease)
median(readme_df$linsear_write_formula)
median(contributing_df$reading_time)
median(contributing_df$linsear_write_formula)
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
readme_reading_ease
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
# establishing the color scheme
subdirColors <-
setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
, levels(contributing_df$subdir)  )
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
ylab("contributing density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
ylab("contributing density") +
xlim(-10, 90) +
theme_bw() +
theme(legend.position = "top")
contributing_reading_ease
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
# plotting contributing linsear writing formula
contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-30, 30) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 90) +
ylab("contributing density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 70) +
guides(fill="none", color="none")+
theme_bw()
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw readme_reading_ease, readme_reading_time_plot, nrow = 2)
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, nrow = 2)
readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-10, 30) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing linsear writing formula
contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 30) +
guides(fill="none", color="none")+
theme_bw()
readme_mcalpine_eflaw <- ggplot(readme_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 60) +
guides(fill="none", color="none")+
theme_bw()
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
scale_color_manual(values = subdirColors) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-10, 60) +
guides(fill="none", color="none")+
theme_bw()
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-5, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
#plotting readme reading time
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-5, 90) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
xlim(-5, 30) +
ylab("readme density") +
guides(fill="none", color="none")+
theme_bw()
readme_mcalpine_eflaw <- ggplot(readme_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
scale_color_manual(values = subdirColors) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-5, 60) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing linsear writing formula
contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
scale_color_manual(values = subdirColors) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-5, 30) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading time
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
scale_color_manual(values = subdirColors) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-5, 90) +
ylab("contributing density") +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
scale_color_manual(values = subdirColors) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
xlim(-5, 60) +
guides(fill="none", color="none")+
theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
scale_color_manual(values = subdirColors) +
ylab("contributing density") +
xlim(-5, 90) +
theme_bw() +
theme(legend.position = "top")
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)
library(tidyverse)
library(plyr)
library(stringr)
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
#load in data
contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
View(contrib_df)
expanded_contrib_data <- expand_timeseries(contrib_df[1,])
for (i in 2:nrow(contrib_df)){
expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
}
#some expansion needs to happens for each project
expand_timeseries <- function(project_row) {
longer <- project_row |>
pivot_longer(cols = ends_with("new"),
names_to = "window",
values_to = "count") |>
unnest(count) |>
mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
mutate(is_collab = as.numeric(str_detect(window, "collab")))
return(longer)
}
expanded_contrib_data <- expand_timeseries(contrib_df[1,])
View(expanded_contrib_data)